Question

我要使用大量格式正确的时间序列数据，以用于预测问题。数据的结构形式如下：

2017-09-26 10:11:57    0.073648
2017-09-26 10:12:57    0.137538
2017-09-26 10:13:57    0.200694
2017-09-26 10:14:57    0.254013
...

将此表示为np.array：

array([0.07364818, 0.13753798, 0.20069409, ..., 0.47428173, 0.47428599,
   0.45940167])

到目前为止，我的模型如下：

序列

class Sequence(nn.Module):
    def __init__(self):
        super(Sequence, self).__init__()
        self.lstm1 = nn.LSTMCell(1, 51)
        self.lstm2 = nn.LSTMCell(51, 51)
        self.linear = nn.Linear(51, 1)

    def forward(self, input, future = 0):
        outputs = []
        h_t = torch.zeros(input.size(0), 51, dtype=torch.double)
        c_t = torch.zeros(input.size(0), 51, dtype=torch.double)
        h_t2 = torch.zeros(input.size(0), 51, dtype=torch.double)
        c_t2 = torch.zeros(input.size(0), 51, dtype=torch.double)

        for i, input_t in enumerate(input.chunk(input.size(1), dim=1)):
            h_t, c_t = self.lstm1(input_t, (h_t, c_t))
            h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))
            output = self.linear(h_t2)
            outputs += [output]

        for i in range(future):# if we should predict the future
            h_t, c_t = self.lstm1(output, (h_t, c_t))
            h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))
            output = self.linear(h_t2)
            outputs += [output]
        outputs = torch.stack(outputs, 1).squeeze(2)
        return outputs

火车

# set random seed to 0
np.random.seed(0)
torch.manual_seed(0)

split = int(len(CO) * 0.7)

train = torch.from_numpy(CO[:split])
valid = torch.from_numpy(CO[split:])

# build the model
seq = Sequence()
seq.double()
criterion = nn.MSELoss()

# use LBFGS as optimizer since we can load the whole data to train
optimizer = optim.LBFGS(seq.parameters(), lr=0.8)

for i in range(15):
    print('STEP: ', i)

    def closure():
        optimizer.zero_grad()
        out = seq(input)
        loss = criterion(out, target)
        print('loss:', loss.item())
        loss.backward()
        return loss

    optimizer.step(closure)

    with torch.no_grad():
        future = 1000
        pred = seq(test_input, future=future)
        loss = criterion(pred[:, :-future], test_target)
        print('test loss:', loss.item())
        y = pred.detach().numpy()

我收到的错误指出：

RuntimeError：尺寸超出范围（预计在[-1，0]范围内，但得到1）

我不确定我理解这是什么原因或如何解决。任何建议将不胜感激。

谢谢

Pytorch时间序列预测

0 个答案: